科研 Skill

论文检索助手

paper-lookup

跨学术数据库检索论文元数据

官方收录发布者 kdense-claude-scientific-skills安全审核通过v0.1.1更新于 2026-11-06

Skill 说明

10 个学术库 REST 检索一站式入口(PubMed / PMC / bioRxiv / medRxiv / arXiv / OpenAlex / Crossref / Semantic Scholar / CORE / Unpaywall),输入关键词 / 标题 / DOI,输出统一格式 JSON 论文列表(title / authors / year / abstract / DOI / venue / 引用数),全部免 key 公共 API | 输入:关键词 / 标题 / DOI | 输出:统一格式 JSON 论文列表(title / authors / year / abstract / DOI / venue / 引用数);覆盖 PubMed / PMC / bioRxiv / arXiv / OpenAlex / Crossref / Semantic Scholar / CORE / Unpaywall

SKILL.md

Paper Lookup

Use the available tools to find papers and verify them against authoritative sources.

Core Workflow

  1. Start with web search for ordinary lookups. When available, prefer web_search for topic, title, author, DOI/PMID, and preprint lookups. For a known URL, open it directly with web_fetch. You can target a site such as PubMed or arXiv in the web query.

  2. Verify the useful hits. Use web_fetch on publisher, journal, DOI, or official repository pages. Check the title, authors, year, and identifier where available. For findings about the paper, use the abstract or full text from the source page. Search snippets are leads. Return the verified papers once they answer the request.

  3. Use an academic API when it adds something the task needs. Examples include an explicitly requested database or query syntax, a reproducible systematic search, a batch export, identifier conversion, a citation graph, or missing results or metadata after web search. If web search is unavailable, choose a relevant database using the guide below. OpenAlex and the arXiv API are optional for ordinary lookups.

  4. Read the relevant reference file before an API call. The files in references/ contain endpoint details, query formats, and examples. See Making API Calls for transport and error handling.

  5. Return results. Give the verified citation, source link, and relevance. Report gaps and distinguish a failed query from an empty result. For API-based requests, list the databases and endpoints queried and include the requested structured results.

Database Selection Guide

Use this guide after deciding that a database API is needed.

By Use Case

User is asking about...Primary database(s)Also consider
Papers on a biomedical topicPubMedSemantic Scholar, OpenAlex
Full text of a biomedical articlePMCCORE
Biology preprintsbioRxivSemantic Scholar, OpenAlex
Health/medical preprintsmedRxivSemantic Scholar, OpenAlex
Physics, math, or CS preprintsarXivSemantic Scholar, OpenAlex
Papers across all fieldsOpenAlexSemantic Scholar, Crossref
A specific paper by DOICrossrefUnpaywall, Semantic Scholar
Open access PDF for a paperUnpaywallCORE, PMC
Citation graph (who cites whom)Semantic ScholarOpenAlex
Author's publicationsSemantic ScholarOpenAlex
Paper recommendationsSemantic Scholar--
Full text (any field)COREPMC (biomedical only)
Journal/publisher metadataCrossrefOpenAlex
Funder informationCrossrefOpenAlex
Convert between PMID/PMCID/DOIPMC (ID Converter)Crossref
Recent preprints by datebioRxiv, medRxivarXiv

Cross-Database Queries

User is asking about...Databases to query
Everything about a paper (metadata + citations + OA)Crossref + Semantic Scholar + Unpaywall
Comprehensive literature searchPubMed + OpenAlex + Semantic Scholar
Find and read a paperPubMed (find) + Unpaywall (OA link) + PMC or CORE (full text)
Preprint and its published versionbioRxiv/medRxiv + Crossref
Author overview with citation metricsSemantic Scholar + OpenAlex

When a query spans multiple needs (e.g., "find papers about CRISPR and get me the PDFs"), query the relevant databases in parallel.

Common Identifier Formats

Different databases use different identifier systems. If a query fails, the identifier format may be wrong.

IdentifierFormatExampleUsed by
DOI10.xxxx/xxxxx10.1038/nature12373All databases
PMIDInteger34567890PubMed, PMC, Semantic Scholar
PMCIDPMC + digitsPMC7029759PMC, Europe PMC
arXiv IDYYMM.NNNNN2103.15348arXiv, Semantic Scholar
OpenAlex IDW + digitsW2741809807OpenAlex
Semantic Scholar ID40-char hex649def34f8be...Semantic Scholar
ORCID0000-XXXX-XXXX-XXXX0000-0001-6187-6610OpenAlex, Crossref
ISSNXXXX-XXXX0028-0836Crossref, OpenAlex

Cross-referencing IDs: Semantic Scholar accepts DOI, PMID, PMCID, and arXiv ID via prefixes (e.g., DOI:10.1038/nature12373, PMID:34567890, ARXIV:2103.15348). OpenAlex accepts DOI and PMID via prefixes (doi:10.1038/..., pmid:34567890). Use the PMC ID Converter to translate between PMID, PMCID, and DOI.

API Keys and Access

Most of these databases are fully open. A few benefit from API keys for higher rate limits.

Databases requiring or benefiting from API keys

DatabaseEnv VariableRequired?Registration
NCBI (PubMed, PMC)NCBI_API_KEYNo (3 req/s without, 10 with)https://www.ncbi.nlm.nih.gov/account/settings/
CORECORE_API_KEYYes for full texthttps://core.ac.uk/services/api
Semantic ScholarS2_API_KEYNo (shared pool without)https://www.semanticscholar.org/product/api#api-key-form
OpenAlexOPENALEX_API_KEYRecommendedhttps://openalex.org/settings/api

Fully open databases (no key needed)

DatabaseNotes
bioRxiv / medRxivNo auth, no documented rate limits
arXivNo auth, max 1 request per 3 seconds
CrossrefNo auth; add mailto param for polite pool (2x rate limit)
UnpaywallNo auth; requires email parameter

Loading API keys

  1. Check the environment first -- the key may already be exported (e.g., $NCBI_API_KEY).
  2. Fall back to .env -- check .env in the current working directory.
  3. Proceed without -- most APIs still work at lower rate limits. Tell the user which key is missing and how to get one.

Making API Calls

Use your environment's HTTP fetch tool to call REST endpoints:

PlatformHTTP Fetch ToolFallback
Claude CodeWebFetchcurl via Bash
Gemini CLIweb_fetchcurl via shell
Windsurfread_url_contentcurl via terminal
CursorNo dedicated fetch toolcurl via run_terminal_cmd
Codex CLINo dedicated fetch toolcurl via shell
ClineNo dedicated fetch toolcurl via execute_command

If the fetch tool fails, fall back to curl via whatever shell tool is available.

Special cases

  • arXiv returns Atom XML, not JSON. Parse it or use curl and extract the relevant fields. Consider piping through a simple parser if available.
  • PMC eFetch returns JATS XML for full text. This is expected -- full text articles are in XML format.
  • Crossref and Unpaywall benefit from including a mailto parameter or email for the polite/fast pool.

Request guidelines

  • For NCBI APIs (PubMed, PMC): max 3 req/sec without key, 10 with key. Make requests sequentially.
  • For arXiv: max 1 request every 3 seconds. Be patient.
  • For Crossref: 5 req/sec (public), 10 req/sec (polite pool with mailto).
  • For other APIs with no strict limits, you can query multiple databases in parallel.
  • If you get HTTP 429 (rate limit), wait briefly and retry once.

Error recovery

  1. Check the identifier format -- use the Common Identifier Formats table. A PMID won't work in arXiv, an arXiv ID won't work in PubMed directly.
  2. Try alternative identifiers -- if a DOI fails in one database, try the title or PMID instead.
  3. Try a different database -- if PubMed returns nothing for a CS paper, try Semantic Scholar or OpenAlex.
  4. Report the failure -- tell the user which database failed, the error, and what you tried instead.

Output Format

For ordinary lookups, return the verified citations with links and a short relevance note. For database-specific or structured requests, use this format:

## Databases Queried
- **PubMed** -- esearch + esummary for "CRISPR gene therapy"
- **Unpaywall** -- DOI lookup for 10.1038/...

## Results

### PubMed
[raw JSON response or formatted results]

### Unpaywall
[raw JSON response]

If API results are large, present the most relevant portion and note that more data is available. Include raw JSON or parsed XML when requested.

Available Databases

Read the relevant reference file before making any API call.

Biomedical Literature

DatabaseReference FileWhat it covers
PubMedreferences/pubmed.md37M+ biomedical citations, abstracts, MeSH terms
PMCreferences/pmc.md10M+ full-text biomedical articles (JATS XML), ID conversion

Preprint Servers

DatabaseReference FileWhat it covers
bioRxivreferences/biorxiv.mdBiology preprints (browse by date/DOI, no keyword search)
medRxivreferences/medrxiv.mdHealth sciences preprints (browse by date/DOI, no keyword search)
arXivreferences/arxiv.mdPhysics, math, CS, biology, economics preprints (keyword search, Atom XML)

Multidisciplinary Indexes

DatabaseReference FileWhat it covers
OpenAlexreferences/openalex.md250M+ works, authors, institutions, topics, citation data
Crossrefreferences/crossref.md150M+ DOI metadata, journals, funders, references
Semantic Scholarreferences/semantic-scholar.md200M+ papers, citation graphs, AI-generated TLDRs, recommendations

Open Access & Full Text

DatabaseReference FileWhat it covers
COREreferences/core.md37M+ full texts from OA repositories worldwide
Unpaywallreferences/unpaywall.mdOA status and PDF links for any DOI

常见问题

论文检索助手能做什么?

10 个学术库 REST 检索一站式入口(PubMed / PMC / bioRxiv / medRxiv / arXiv / OpenAlex / Crossref / Semantic Scholar / CORE / Unpaywall),输入关键词 / 标题 / DOI,输出统一格式 JSON 论文列表(title / authors / year / abstract / DOI / venue / 引用数),全部免 key 公共 API | 输入:关键词 / 标题 / DOI | 输出:统一格式 JSON 论文列表(title / authors / year / abstract / DOI / venue / 引用数);覆盖 PubMed / PMC / bioRxiv / arXiv / OpenAlex / Crossref / Semantic Scholar / CORE / Unpaywall。

如何安装论文检索助手?

在科搭 Codar 左侧点击「插件」,在「组件」页签搜索「论文检索助手」并安装;在 Claude Code 或 Codex 中可以发送本页的安装提示词,或下载 Skill 包后解压到 ~/.claude/skills 或 ~/.codex/skills。

论文检索助手需要哪些权限?

该科研 Skill声明需要:本地文件、联网。安装前会再次列出,由你确认后才会生效。

论文检索助手经过官方审核吗?

是。SpeedSkills 收录的每个版本都会记录内容摘要与权限声明,当前版本已通过安全审核。